January 25–27, 2021
Join Genedata experts at the SLAS2021 Virtual conference.
Don't miss the opportunity to see how Genedata Screener® analyzes, visualizes, and manages screening data from in-vitro screening assay technologies across the enterprise, including very complex as well as ultra-high throughput experiments. Its screening-oriented business logic enables rapid processing and comprehensive analysis of complete campaigns.
If you would like to schedule a meeting in advance for our virtual booth or receive more information on Genedata Screener, please contact screener(at)genedata.com.
You also have the chance to find out more about our new solution, Genedata Imagence®, a high content screening (HCS) image analysis software based on deep learning. To get more information about Genedata Imagence or to arrange a meeting, please contact imagence(at)genedata.com.
Recommended Oral Presentations
Automated Analysis of Biphasic PROTAC Dose Response Data at Scale in Drug Development
Ganesh Kadamur, PhD, AstraZeneca
Metabolomics in Drug Discovery
Monday, January 25 | 9:00–9:00 am EST
A precise, quantitative and reproducible estimation of drug parameters is essential for robust Structure Activity Relationship (SAR) driven drug development. Traditional small molecule screening for inhibitors of the majority of targets yields monotonic dose response curves with a sigmoidal shape, characterised by a plateau at high drug concentrations. The compound is evaluated by fitting to a Hill model, leading to measurements of the maximum effect (efficacy) and the concentration for half maximal effect (IC50). In contrast, some drug modalities lead to a distinct dose response profile, marked by a loss of efficacy after the plateau. Such a “hook” effect is particularly relevant for PROteolysis TArgeting Chimeras (PROTACs). PROTACs are an exciting new modality that induce degradation rather than inhibition of targets, thus enabling the targeting of proteins without defined active sites such as scaffolding complexes. PROTACs induce ternary complex formation between the target, an endogenous E3 ligase and the PROTAC leading to protein degradation. Consequently, at high concentrations, PROTAC assays often exhibit a hook effect due to formation of independent binary complexes. Application of the standard Hill model to data with a hook effect results in misestimation of both IC50 and efficacy. Accounting for the hook effect is essential to extract the best understanding of the data and making informed SAR decisions.
We have developed a bell-shaped biphasic model to allow double sigmoidal curve fitting, with parameters to describe both sigmoidal parts of the data and crucially, confidence levels around the efficacy. This algorithm overcomes the challenge of achieving convergence unlike complex non-linear statistical models, making it usable in high-throughput settings ( >100 compounds/run). The advanced algorithm we have developed can thus achieve more accurate estimation of IC50 and efficacy to drive medicinal chemistry SAR. We have implemented the fit method in Genedata Screener for the analysis of high throughput experimental data. This method also features automated selection of the correct model, Hill or bell-shaped, and automatic data masking, as appropriate. Application of this method to real world PROTACs data has demonstrated its ability to reduce manual intervention and deliver accurate curve fit parameters, leading to greater confidence in drug SAR insights. Further, the novel curve fit algorithm is able to quantitatively describe data from non-PROTACs targets too, showcasing its flexibility and applicability across projects independent of the underlying biology.
Fueling Drug Discovery with AI-ready Data: Running Automated Assay Cascades in the Digital Lab
Cameron Scott, Scientific Account Manager, Genedata
Monday, January 25 | 5:00–5:30 pm EST
Drug discovery is an expensive, long and uncertain endeavor. Following its successive industrialization during the past three decades, it is now undergoing a digital transformation, with the goals of better leveraging scientific creativity, experience distributed across teams, and institutional knowledge while favorably tipping the cost-success balance of discovery. An important part of this process is data workflow automation, first introducing and then automating digital lab workflows.
Compound screening is the process fueling the discovery cascade in many instances, and as such has pioneered robotic process automation in small molecule discovery and increasingly also in biologics discovery. In this tutorial, we show how the corresponding data workflow is being realized and automated, enabling fast and rich assay cascades to fuel project team decisions and in-silico predictions.
We will guide you through the automation of assay registration and experiment design, data capture, data processing, QC, and analysis. We will touch on the required semantic annotation, quality assurance, standardization and experiment-adaptive business logic to produce FAIR data in the process.
The result are concise, deep bioactivity result sets, where decision-ready summaries efficiently enable the scientist to plan the next experiment, and AI-ready, fully structured and annotated multivariate data sets inform automated in-silico predictions. A corresponding case study will close the presentation.
AI-powered High Content Screening Analytics with Genedata Imagence 3.0
Matthias Fassler, Imagence Project Lead, Genedata
Tuesday, January 26 | 1:30–2:00 pm EST
In this tutorial we showcase the future of automated HCS image analysis in Biopharma R&D, Genedata Imagence. Imagence combines state-of-the-art deep learning methods with protocols for efficient training and incremental training data enrichment, features intuitive representations of data and knowledge, and runs on a fully scalable infrastructure. Matching the needs of today’s most challenging bioassays, it allows screening scientists to reliably detect stable endpoints for primary drug response, assess toxicity and safety-relevant effects, and to discover new phenotypes and compound classes.
In this tutorial we show how Imagence enables training of a new deep learning model in a few simple steps and how to apply the trained model to process a production HCS, producing results on an industrial scale with superior quality. We also present novelties in Imagence version 3: The incremental training data enrichment protocol which enables efficient retraining of a network to automatically adapt to slightly altered experimental conditions and a new classification uncertainty measure that allows to rapidly spot any data quality issues. These are examples of Imagence’s continuous development towards bringing ultimate efficiency and ease-of-use to HCS analysis.
Compound Combination Screening Special Interest Group (SIG)
Oliver Leven & Spencer Carson, Genedata
Wednesday, January 27 | 12:00–1:00 pm EST